14 posts published in the last hour
- 09:37ASIWorld: Benchmarking Autonomous Agents in a Persistent Survival Sandbox
- 09:37GREAT-ESDD: Graph Edge Attention Network for Effectively Steered Delivery Decisions
- 09:37Counterfactual Regret for Reflective Agents with Lean-Verified Guarantees
- 09:37Open models have real benefits. Do they outweigh the risks?
- 09:37A Reference Architecture for Integrating Agentic AI into Enterprise Software: Responsibilities, Interactions, and Variability
- 09:37AI labs are buying data from dead startups to train their models
- 09:37CESNET-TimeSeries26: A Multi-Year Network Traffic Time Series Dataset for Annual Seasonality, Concept Drift, and Long-Term Anomaly Detection
- 09:05CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation
- 09:05ProgAgent: Learning Tool Orchestration through Programmatic Training
- 09:05GateSight: Recurrent Memory Anticipates Attention Memory for Query-Agnostic KV Eviction in Hybrid LLMs
- 09:05[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
- 09:05LYNX: Analytical Program Synthesis via Grounding and Closed-Loop Refinement
- 09:05Z.ai GLM-Legal Beats Claude Fable 5 and Kimi K3 on Harvey LAB
- 09:04How Should a Camera-First AI Agent Work?